A Data-analytical System to Predict Therapy Success for Obese Children

Nurten Öksüz, Iaroslav Shcherbatyi, Tobias Kowatsch, Wolfgang Maaß

In: ICIS 2018 - International Conference on Information Systems. International Conference on Information Systems (ICIS-2018) December 13-16 San Francisco CA United States Springer 12/2018.


Childhood obesity is an increasingly pervasive problem. Traditional therapy programs are time- and cost-intensive. Furthermore, success of therapy is often not guaranteed. Typically, success of therapies is determined by comparison of body mass index (BMI) before and after a therapy. In this paper, we present a Data-analytical Information Systems (DAIS) that provides predictions of future BMI changes before conducting a therapy. The DAIS considers current parameters like age as well as heart rate during a standardized exercise. By predicting outcomes of a therapy, healthcare practitioners could personalize standard therapies and improve the outcome. We collected data from randomized clinical trial and trained Machine Learning models to estimate whether BMI will decrease after therapy with 85% accuracy. Accuracy of predictions is compared with domain experts’ predictions. Further, we present empirical results of the domain experts' perception regarding the proposed DAIS. Our DAIS provides positive evidence as a tool for personalized medicine.

ICIS_2018_Revison.pdf (pdf, 457 KB)

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence